{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U7WAR3LYUYWZBBNA7HHL7WVT2V","short_pith_number":"pith:U7WAR3LY","schema_version":"1.0","canonical_sha256":"a7ec08ed78a62d9085a0f9cebfdab3d54491a5265fa57691897e2683764ebd55","source":{"kind":"arxiv","id":"2209.01754","version":5},"attestation_state":"computed","paper":{"title":"Learning from a Biased Sample","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Lihua Lei, Roshni Sahoo, Stefan Wager","submitted_at":"2022-09-05T04:19:16Z","abstract_excerpt":"The empirical risk minimization approach to data-driven decision making requires access to training data drawn under the same conditions as those that will be faced when the decision rule is deployed. However, in a number of settings, we may be concerned that our training sample is biased in the sense that some groups (characterized by either observable or unobservable attributes) may be under- or over-represented relative to the general population; and in this setting empirical risk minimization over the training set may fail to yield rules that perform well at deployment. We propose a model "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.01754","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2022-09-05T04:19:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eb67b536422be88092c1a402af807cebff2a9bcf59a1e9e470e5285d35e45427","abstract_canon_sha256":"db9db85b560744494d02f19d728df9667a5caf8a8b3950666359ba2d4f0ccf8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:12.444357Z","signature_b64":"haxh02a/FPpTFkSfNuORonW+RpekFTYade63TSLlQYSq0cMgc1KvGffgZ5LvmxpBSrpbMbQ24ef5KdDz4ef9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ec08ed78a62d9085a0f9cebfdab3d54491a5265fa57691897e2683764ebd55","last_reissued_at":"2026-06-26T01:15:12.443831Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:12.443831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from a Biased Sample","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Lihua Lei, Roshni Sahoo, Stefan Wager","submitted_at":"2022-09-05T04:19:16Z","abstract_excerpt":"The empirical risk minimization approach to data-driven decision making requires access to training data drawn under the same conditions as those that will be faced when the decision rule is deployed. However, in a number of settings, we may be concerned that our training sample is biased in the sense that some groups (characterized by either observable or unobservable attributes) may be under- or over-represented relative to the general population; and in this setting empirical risk minimization over the training set may fail to yield rules that perform well at deployment. We propose a model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01754","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.01754/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.01754","created_at":"2026-06-26T01:15:12.443893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.01754v5","created_at":"2026-06-26T01:15:12.443893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01754","created_at":"2026-06-26T01:15:12.443893+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7WAR3LYUYWZ","created_at":"2026-06-26T01:15:12.443893+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7WAR3LYUYWZBBNA","created_at":"2026-06-26T01:15:12.443893+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7WAR3LY","created_at":"2026-06-26T01:15:12.443893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.00320","citing_title":"Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00563","citing_title":"A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2410.10704","citing_title":"Estimation beyond Missing (Completely) at Random","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20710","citing_title":"Assessing Estimate of CATE from Observational Data via an RCT Study","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05591","citing_title":"In-Context Positive-Unlabeled Learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V","json":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V.json","graph_json":"https://pith.science/api/pith-number/U7WAR3LYUYWZBBNA7HHL7WVT2V/graph.json","events_json":"https://pith.science/api/pith-number/U7WAR3LYUYWZBBNA7HHL7WVT2V/events.json","paper":"https://pith.science/paper/U7WAR3LY"},"agent_actions":{"view_html":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V","download_json":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V.json","view_paper":"https://pith.science/paper/U7WAR3LY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.01754&json=true","fetch_graph":"https://pith.science/api/pith-number/U7WAR3LYUYWZBBNA7HHL7WVT2V/graph.json","fetch_events":"https://pith.science/api/pith-number/U7WAR3LYUYWZBBNA7HHL7WVT2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V/action/storage_attestation","attest_author":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V/action/author_attestation","sign_citation":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V/action/citation_signature","submit_replication":"https://pith.science/pith/U7WAR3LYUYWZBBNA7HHL7WVT2V/action/replication_record"}},"created_at":"2026-06-26T01:15:12.443893+00:00","updated_at":"2026-06-26T01:15:12.443893+00:00"}